first commit

.gitattributes

@@ -0,0 +1,41 @@
+images/attractions/recoAll_attractions_1.jpg filter=lfs diff=lfs merge=lfs -text
+images/attractions/recoAll_attractions_2.jpg filter=lfs diff=lfs merge=lfs -text
+images/attractions/recoAll_attractions_3.jpg filter=lfs diff=lfs merge=lfs -text
+images/attractions/recoAll_attractions_4.jpg filter=lfs diff=lfs merge=lfs -text
+images/demo.jpg filter=lfs diff=lfs merge=lfs -text
+main_axcl filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l12_together.axmodel filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l13_together.axmodel filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l27_together.axmodel filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/Qwen2.5-VL-7B-Instruct_vision.axmodel filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l18_together.axmodel filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l26_together.axmodel filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l6_together.axmodel filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l9_together.axmodel filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l15_together.axmodel filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l17_together.axmodel filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l14_together.axmodel filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l23_together.axmodel filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l5_together.axmodel filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l10_together.axmodel filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l20_together.axmodel filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l25_together.axmodel filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_post.axmodel filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l16_together.axmodel filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l4_together.axmodel filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l7_together.axmodel filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l8_together.axmodel filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/model.embed_tokens.weight.bfloat16.bin filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l19_together.axmodel filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l1_together.axmodel filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l3_together.axmodel filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l11_together.axmodel filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l21_together.axmodel filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l22_together.axmodel filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l24_together.axmodel filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l2_together.axmodel filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l0_together.axmodel filter=lfs diff=lfs merge=lfs -text
+images/ filter=lfs diff=lfs merge=lfs -text
+images/attractions filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/model.embed_tokens.weight.float32.bin filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/model.embed_tokens.weight.npy filter=lfs diff=lfs merge=lfs -text

Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/Qwen2.5-VL-7B-Instruct_vision.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f2deda5902bd4854618a0f3b20cb4ea17d21988bf9aa64806d3d5ff1a245e2f
+size 794112805

Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/model.embed_tokens.weight.bfloat16.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bf25d9fd2cf7a3961e5f18b0964e13c130e605a5a3b5724f7781e624552b6c4
+size 1089994752

Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/model.embed_tokens.weight.float32.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c0858fa0e499dd6651dd23ea887bc6e7129cd83423308997de426564287d5e7
+size 2179989504

Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/model.embed_tokens.weight.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:310f46c33a3b652de9363b101912f0421ec160d81e36c97f4c32269005327b67
+size 2179989632

Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l0_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33ca72437766dfa13c71b5ff5e025a85c9445b99afcaa4b63b2e172ac69a82ec
+size 285621242

Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l10_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c01ebe7041c6a0c7800f8e7a3bce0f2e7c9efe49d75706d516768ce9db9ce9cd
+size 285621242

Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l11_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b1b711581f736c2ce9d0dc45cd2f45b45eddc52a157699c99fb4e3080205112
+size 285621242

Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l12_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f33e7af2c068f7d55e0a48ef9a1d039bf9515e7e069fe3c7f8770b4d7045d876
+size 285621242

Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l13_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0aa2e4ee593482f825af6b66c1cf1c458a9eeefd80651573293d1be812bbe48
+size 285621242

Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l14_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3f2f6c73a670b1356e03cf053bc036bc6785e3dd089a603dd4c87b246b0a496
+size 285621242

Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l15_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bda527847add50f6a7e373b9064cbda64e45ae2f9f579eb29dd160a901a0cca9
+size 285621242

Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l16_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:511eb8cf37e2d5b2b73f2ee3dc56650ebf7bbb2671ec02b55d7c9e4b83f7fd02
+size 285621242

Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l17_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9136add22236498acb77f7e0670c2439c2621aa0c6c92e6ff0f5eccde218cbd
+size 285621242

Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l18_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91e84afd6ff3675daa143459b0547d06b817751856a31c1eb1134c9112170b81
+size 285621242

Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l19_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adf57236f34d8c60adb1b26d1dc17a8eae75ab7eb5232c1ded7bb155425f7032
+size 285621242

Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l1_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:095b2e6ef6db8c8eaf4d0e84aaa39883118d1ff62f4cc155bd7e8daf7d884971
+size 285621242

Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l20_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c74edcfbe5f52e389421b2f3099a9cc2d83317b51cbe8c59b94b56b14375d421
+size 285621242

Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l21_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2606f79594be5072bf9866d6f9931b361a226bf47251affa93aeb930ce7a261e
+size 285621242

Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l22_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:708d428c078dac40b2052a8f1c40597335e22b379655e80e7348c8acd51b33e7
+size 285621658

Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l23_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee3bdec5b92a7b1bf61e665fc852d9b22ce8b1858ccc65b7791f8bf113948fae
+size 285621626

Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l24_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:740babbd692b55c4a78882178e2705443968c889726093a5451dd46a2f90744c
+size 285621658

Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l25_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91e481b168346f8edb01a3ea711a1b46bc97fe6d77b8752f627c121677dfc3e5
+size 285621818

Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l26_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7158799c32c6dc45c33813310eeb8d52c2a2d36fb785743dcdc0d7b2d4da7ef6
+size 285621658

Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l27_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35ee2b6415bbd3bdd5486c02707d1e6ced0902a18e9be471f8409841566efacf
+size 285621242

Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l2_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6476fedfea3ec802b39085cc51dd9b3f453724f6e6a46c041fe9eb56192ee2e
+size 285621242

Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l3_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1d2942ff0559e6ea0e255fd48b40fbf9c6c25e022109e7c3ce0f45c8c0369f7
+size 285621242

Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l4_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:528d6a0f5e5dedcda6b4c78f67261361cf49f05b9ba13c2a4c360aaee47eaa0f
+size 285621242

Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l5_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a2829258b7bc706e93aee2d01ed6dd4517700fa3dc3508da0fc4d6ac06bc944
+size 285621242

Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l6_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3b407cc02fe041c65f36a0caab65e2a2e8ce9243ea148d624588173f878a184
+size 285621242

Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l7_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a10bfecd6ec7402d493724b6b97f18260a2c8e140c7faeaa503a107c820c1083
+size 285621242

Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l8_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c66ddb104323b14b7ca93c9ce5d8683fea39d966f0da26dea522133c53ea88f
+size 285621242

Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_p128_l9_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abd237e9226ef1dc5728209b5798d5abab4839e75363868c4b265c76c9d87c55
+size 285621242

Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280/qwen2_5_vl_post.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7447f2fd00a4ee394d6071a0924ae23c10139515e2162fe51cba345e6ee96ae6
+size 594206287

README.md

@@ -0,0 +1,163 @@
+---
+license: mit
+language:
+- en
+- zh
+base_model:
+- Qwen/Qwen2.5-VL-7B-Instruct
+pipeline_tag: image-text-to-text
+library_name: transformers
+tags:
+- Qwen2.5-VL
+- Qwen2.5-VL-7B-Instruct
+- Int8
+- VLM
+---
+
+# Qwen2.5-VL-7B-Instruct
+
+This version of Qwen2.5-VL-7B-Instruct has been converted to run on the Axera NPU using **w8a16** quantization.
+
+This model has been optimized with the following LoRA: 
+
+Compatible with Pulsar2 version: 3.4
+
+## Convert tools links:
+
+For those who are interested in model conversion, you can try to export axmodel through the original repo : 
+https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct
+
+[Pulsar2 Link, How to Convert LLM from Huggingface to axmodel](https://pulsar2-docs.readthedocs.io/en/latest/appendix/build_llm.html) 
+
+[AXera NPU HOST LLM Runtime](https://github.com/AXERA-TECH/Qwen2.5-VL-7B-Instruct.axera) 
+
+
+## Support Platform
+
+- AX650
+  - AX650N DEMO Board
+  - [M4N-Dock(爱芯派Pro)](https://wiki.sipeed.com/hardware/zh/maixIV/m4ndock/m4ndock.html)
+  - [M.2 Accelerator card](https://axcl-docs.readthedocs.io/zh-cn/latest/doc_guide_hardware.html)
+
+**Image Process**
+|Chips| input size | image num | image encoder | ttft(320 tokens) | w8a16 | DDR | Flash |
+|--|--|--|--|--|--|--|--|
+|AX650| 448*448 | 1 | 760 ms | 3500 ms | 2.0 tokens/sec| 10.0 GiB |  9.8 GiB  |
+
+**Video Process**
+|Chips| input size | image num | image encoder |ttft(512 tokens) | w8a16 | DDR | Flash |
+|--|--|--|--|--|--|--|--|
+|AX650| 308*308 | 8  | 1400 ms | 5400 ms | 6.1 tokens/sec| 10.0 GiB |  9.8 GiB  | 
+
+The DDR capacity refers to the CMM memory that needs to be consumed. Ensure that the CMM memory allocation on the development board is greater than this value.
+
+## How to use
+
+Download all files from this repository to the device
+
+**If you using AX650 Board**
+```
+(base) axera@dell:~/lhj/Qwen2.5-VL-7B-Instruct$ tree -L 2
+.
+├── images
+├── main_axcl
+├── post_config.json
+├── Qwen2.5-VL-7B-Instruct-AX650-chunk_prefill_1280
+│   ├── model.embed_tokens.weight.bfloat16.bin
+│   ├── Qwen2.5-VL-7B-Instruct_vision.axmodel
+│   ├── qwen2_5_vl_p128_l0_together.axmodel
+......
+│   └── qwen2_5_vl_post.axmodel
+├── qwen2_5_vl_7b_tokenizer
+├── qwen2_tokenizer_images.py
+├── qwen2_tokenizer_video_308.py
+├── README.md
+├── run_qwen2_5vl_image.sh
+├── run_qwen2_5vl_video.sh
+└── video
+
+```
+
+### Prepare tokenizer server
+
+#### Install transformer
+
+```
+pip install transformers==4.41.1 jinja2
+```
+
+### Demo Run
+
+#### Image understand demo
+
+##### start tokenizer server for image understand demo
+
+```
+python3 qwen2_tokenizer_images.py --port 12345
+```
+
+##### run image understand demo
+
+- input text
+
+```
+What are these attractions? Please give their names in Chinese and English
+```
+
+- input image
+
+![](./images/attractions)
+
+```
+(base) axera@dell:~/lhj/Qwen2.5-VL-7B-Instruct$ bash run_qwen2_5vl_image.sh 
+[I][                            Init][ 162]: LLM init start
+
+[I][                            Init][ 267]: IMAGE_CONTEXT_TOKEN: 151655, IMAGE_START_TOKEN: 151652
+[I][                            Init][ 328]: image encoder output float32
+[I][                            Init][ 456]: LLM init ok
+Type "q" to exit, Ctrl+c to stop current running
+prompt >> What are these attractions? Please give their names in Chinese and English
+image >> images/attractions
+images/attractions/recoAll_attractions_1.jpg
+images/attractions/recoAll_attractions_2.jpg
+images/attractions/recoAll_attractions_3.jpg
+images/attractions/recoAll_attractions_4.jpg
+[I][                          Encode][ 552]: image encode time : 3014.224121 ms, size : 4
+[I][                          Encode][ 594]: input_ids size:1064
+[I][                          Encode][ 602]: offset 15
+[I][                          Encode][ 602]: offset 273
+[I][                          Encode][ 602]: offset 531
+[I][                          Encode][ 602]: offset 789
+[I][                          Encode][ 624]: out_embed size:3813376
+[I][                          Encode][ 626]: position_ids size:7982
+[I][                             Run][ 645]: input token num : 1064, prefill_split_num : 9
+[I][                             Run][ 679]: input_num_token:128
+[I][                             Run][ 679]: input_num_token:128
+[I][                             Run][ 679]: input_num_token:128
+[I][                             Run][ 679]: input_num_token:128
+[I][                             Run][ 679]: input_num_token:128
+[I][                             Run][ 679]: input_num_token:128
+[I][                             Run][ 679]: input_num_token:128
+[I][                             Run][ 679]: input_num_token:128
+[I][                             Run][ 679]: input_num_token:40
+[I][                             Run][ 816]: ttft: 15817.47 ms
+1. **金字塔 (Pyramids)**  
+   - **英文**: Pyramids  
+   - **位置**: ��及 (Egypt)
+
+2. **长城 (Great Wall of China)**  
+   - **英文**: Great Wall of China  
+   - **位置**: 中国 (China)
+
+3. **自由女神像 (Statute of Liberty)**  
+   - **英文**: Statue of Liberty  
+   - **位置**: 美国 (United States)
+
+4. **兵马俑 (Terracotta Army)**  
+   - **英文**: Terracotta Army  
+   - **位置**: 中国 (China)
+
+[N][                             Run][ 969]: hit eos,avg 2.05 token/s
+
+```
+

main_axcl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae3a919e04631a954bb3fe7162d9ebf024ca32dccc960f3f1f6fc6bd7d84a326
+size 1893800

post_config.json

@@ -0,0 +1,14 @@
+{
+    "enable_temperature" : true,
+    "temperature" : 0.1,
+    
+    "enable_repetition_penalty" : false,
+    "repetition_penalty" : 2,
+    "penalty_window" : 30,
+
+    "enable_top_p_sampling" : false,
+    "top_p" : 0.8,
+
+    "enable_top_k_sampling" : true,
+    "top_k" : 10
+}

qwen2_5_vl_7b_tokenizer/chat_template.json

@@ -0,0 +1,3 @@
+{
+    "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
+}

qwen2_5_vl_7b_tokenizer/config.json

@@ -0,0 +1,61 @@
+{
+  "architectures": [
+    "Qwen2_5_VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "vision_start_token_id": 151652,
+  "vision_end_token_id": 151653,
+  "vision_token_id": 151654,
+  "image_token_id": 151655,
+  "video_token_id": 151656,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 128000,
+  "max_window_layers": 28,
+  "model_type": "qwen2_5_vl",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vision_config": {
+    "depth": 32,
+    "hidden_act": "silu",
+    "hidden_size": 1280,
+    "intermediate_size": 3420,
+    "num_heads": 16,
+    "in_chans": 3,
+    "out_hidden_size": 3584,
+    "patch_size": 14,
+    "spatial_merge_size": 2,
+    "spatial_patch_size": 14,
+    "window_size": 112,
+    "fullatt_block_indexes": [
+      7,
+      15,
+      23,
+      31
+    ],
+    "tokens_per_second": 2,
+    "temporal_patch_size": 2
+  },
+  "rope_scaling": {
+    "type": "mrope",
+    "mrope_section": [
+      16,
+      24,
+      24
+    ]
+  },
+  "vocab_size": 152064
+}

qwen2_5_vl_7b_tokenizer/configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "vision-understanding", "allow_remote": true}

qwen2_5_vl_7b_tokenizer/generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 151643,
+  "pad_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "repetition_penalty": 1.05,
+  "temperature": 0.000001,
+  "transformers_version": "4.37.0"
+}

qwen2_5_vl_7b_tokenizer/model.safetensors.index.json

@@ -0,0 +1,736 @@
+{
+  "metadata": {
+    "total_size": 16584333312
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00005-of-00005.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.norm.weight": "model-00004-of-00005.safetensors",
+    "visual.blocks.0.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.0.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.0.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.0.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.0.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.0.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.1.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.1.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.1.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.1.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.1.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.1.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.10.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.10.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.10.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.10.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.10.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.10.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.11.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.11.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.11.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.11.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.11.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.11.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.12.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.12.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.12.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.12.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.12.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.12.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.13.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.13.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.13.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.13.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.13.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.13.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.14.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.14.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.14.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.14.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.14.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.14.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.15.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.15.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.15.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.15.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.15.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.15.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.16.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.16.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.16.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.16.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.16.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.16.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.17.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.17.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.17.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.17.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.17.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.17.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.18.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.18.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.18.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.18.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.18.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.18.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.19.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.19.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.19.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.19.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.19.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.19.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.2.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.2.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.2.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.2.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.2.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.2.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.20.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.20.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.20.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.20.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.20.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.20.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.21.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.21.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.21.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.21.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.21.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.21.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.22.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.22.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.22.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.22.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.22.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.22.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.23.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.23.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.23.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.23.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.23.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.23.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.24.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.24.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.24.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.24.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.24.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.24.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.25.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.25.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.25.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.25.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.25.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.25.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.26.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.26.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.26.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.26.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.26.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.26.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.27.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.27.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.27.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.27.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.27.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.27.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.28.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.28.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.28.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.28.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.28.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.28.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.29.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.29.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.29.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.29.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.29.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.29.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.3.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.3.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.3.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.3.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.3.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.3.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.30.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.30.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.30.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.30.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.30.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.30.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.31.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.31.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.31.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.31.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.31.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.31.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.4.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.4.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.4.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.4.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.4.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.4.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.5.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.5.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.5.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.5.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.5.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.5.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.6.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.6.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.6.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.6.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.6.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.6.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.7.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.7.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.7.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.7.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.7.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.7.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.8.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.8.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.8.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.8.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.8.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.8.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.9.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.9.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.9.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.9.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.9.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.9.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.merger.ln_q.weight": "model-00001-of-00005.safetensors",
+    "visual.merger.mlp.0.bias": "model-00001-of-00005.safetensors",
+    "visual.merger.mlp.0.weight": "model-00001-of-00005.safetensors",
+    "visual.merger.mlp.2.bias": "model-00001-of-00005.safetensors",
+    "visual.merger.mlp.2.weight": "model-00001-of-00005.safetensors",
+    "visual.patch_embed.proj.weight": "model-00001-of-00005.safetensors"
+  }
+}

qwen2_5_vl_7b_tokenizer/preprocessor_config.json

@@ -0,0 +1,19 @@
+{
+  "min_pixels": 3136,
+  "max_pixels": 12845056,
+  "patch_size": 14,
+  "temporal_patch_size": 2,
+  "merge_size": 2,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "processor_class": "Qwen2_5_VLProcessor"
+}